xtract.bot

Match features (ORB)

Try it interactively →

POST /api/image-match-features3 quota units per call · cache hits free

Detect and match feature points between two images. Robust to rotation, scale, and modest lighting changes. Useful for image alignment and panorama stitching.

Detects feature points in two images and finds correspondences between them. The matching is robust to rotation, scale, and modest lighting differences — much more flexible than pixel- level template matching. Useful for image alignment, panorama stitching, motion estimation, and object-pose estimation. Returns each matched pair as `{(x1, y1), (x2, y2), distance}` where distance is the descriptor similarity.

Inputs

NameTypeDefaultDescription
image*fileQuery image bytes.
target*fileTrain image bytes — the second image to match against.
nfeaturesnumber (50…8000)1000Max ORB keypoints per image.
maxMatchesnumber (1…1000)50Cap on returned match pairs.

Response

Modes: json. Cache: yes (24h TTL).

Every response carries x-cache (HIT / MISS / BYPASS), x-cache-signature (stable across identical inputs), and the rate-limit headers listed below.

Quota & limits

Cost per call3 units against the 10,000-unit monthly quota. Cache hits are free — only cache misses decrement.
Burst limit200 requests per rolling minute, shared across all tools.
Max request size50 MiB (base64 inflates file payloads ~33% — the limit applies to the decoded bytes).
Max response size1 MiB
Timeout30s wall clock.
Rate-limit headersX-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Burst-Limit on every response; X-Quota-Warning once 80% of the monthly quota is spent; Retry-After on 429s.

Errors

Errors are JSON with an error string; schema failures add a details object (Zod's flattened field errors).

StatusWhenBody
400Input fails the tool's schema (wrong type, missing required field, malformed base64) or the file bytes can't be parsed as the expected format.{ "error": "invalid inputs", "details": { "fieldErrors": { … } } }
401Missing or invalid X-Api-Key / X-Account-Id headers (or no session when called from the browser).{ "error": "unauthorized" }
404Unknown tool id, or calling /api/* on the website hostname instead of api.xtract.bot.{ "error": "not found" }
413Request body over the tool's max request size, or an image header declaring more megapixels than the tool's pixel budget.{ "error": "…exceeds maxRequestBytes…" }
415Content-Type isn't application/json on the json-body transport.{ "error": "unsupported content-type; expected application/json" }
429Monthly quota or the 200/min burst limit exhausted. Check Retry-After and the X-RateLimit-* headers.{ "error": "monthly quota exceeded", "monthRemaining": 0, … }
5xxConversion engine failure. Safe to retry; if it persists, the input is hitting a bug — please report it.{ "error": "…" }

Code samples

Built from the self-match example.

# Download or substitute the example input:
#   curl -O https://xtract.bot/examples/image-align/sample.png
IMAGE=$(base64 -w0 < sample.png)
# Download or substitute the example input:
#   curl -O https://xtract.bot/examples/image-align/sample.png
TARGET=$(base64 -w0 < sample.png)

curl -X POST https://api.xtract.bot/api/image-match-features \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "X-Account-Id: $XTRACT_ACCOUNT_ID" \
  -H "X-Api-Key: $XTRACT_API_KEY" \
  -d '{
  "image": "'"$IMAGE"'",
  "target": "'"$TARGET"'"
}'